Inference, Fine-Tuning, and Retrieval-Augmented Generation
Abstract
This chapter is a practical introduction to post-training optimization and deployment of large language models (LLMs). Our primary focus will be on two crucial techniques: Retrieval-Augmented Generation (RAG) and fine-tuning, which are essential for enhancing LLM capabilities. We will explore the technical foundations of these methods and discuss the specific scenarios where each approach is most applicable. Next, we turn our attention to inference systems. We will explore the technical background of inference, including the computational processes involved and the metrics used to evaluate their performance. By the end of this chapter, you will have a better understanding of post-training optimization and inference for a deployed LLM.
Read the paper
Related studies
- Knowledge Management Perspective of Generative Artificial Intelligence
- Navigating Generative Artificial Intelligence Promises and Perils for Knowledge and Creative Work
- Characterizing the evolving research on enterprise content management
- Large language models and multimodal foundation models for precision oncology
- From Generative AI to Extended Reality: Multidisciplinary Perspectives on the Challenges, Opportunities, and Future of Educational Computing
- Generative Artificial Intelligence: A New Engine for Advancing Environmental Science and Engineering
Go deeper in Evidence Hub
Evidence Hub adds a study data sheet (design, sample size, evidence level, key numbers), an AI summary and a chat grounded in the paper's text.